Atlas / MCP servers / mnhlt / WebSearch

WebSearchSAFE

mcp/mnhlt/websearch

[Self-hosted] A Model Context Protocol (MCP) server implementation that provides a web search capability over stdio transport. This server integrates with a WebSearch Crawler API to retrieve search results.

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
1 1r · 0w · 0d
Transport
stdio
License
—
Stars
41
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://smithery.ai/server/@mnhlt/WebSearch-MCP)

A Model Context Protocol (MCP) server implementation that provides a web search capability over stdio transport. This server integrates with a WebSearch Crawler API to retrieve search results.

Table of Contents

  • About
  • Installation
  • Configuration
  • Setup & Integration
  • Setting Up the Crawler Service
  • Prerequisites
  • Starting the Crawler Service
  • Testing the Crawler API
  • Custom Configuration
  • Integrating with MCP Clients
  • Quick Reference: MCP Configuration
  • Claude Desktop
  • Cursor IDE
  • Cline
  • Usage
  • Parameters
  • Example Search Response
  • Testing Locally
  • As a Library
  • Troubleshooting
  • Crawler Service Issues
  • MCP Server Issues
  • Development
  • Project Structure
  • Publishing to npm
  • Contributing
  • License

About

WebSearch-MCP is a Model Context Protocol server that provides web search capabilities to AI assistants that support MCP. It allows AI models like Claude to search the web in real-time, retrieving up-to-date information about any topic.

The server integrates with a Crawler API service that handles the actual web searches, and communicates with AI assistants using the standardized Model Context Protocol.

Installation

Installing via Smithery

To instal

Read from source at commit 7d968c432be9OBSERVED · 2026-10-08
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add websearch-mcp -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "websearch-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}
03

Exposed tools (1)

1 read · 0 write · 0 destructive.

ToolRiskDescription
web_searchreadSearch the web for information.\n
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (2 observation(s))
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (2)

LOWInventory / provenance · inv.no_license · CWE-1104
Why it matters. no LICENSE file and no repo licence
Fix. add a licence
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@modelcontextprotocol/sdk, axios, zod, @types/node, ts-node, typescript
Why it matters. 6 dependency range(s) float
Fix. pin exact versions or ship a lockfile

Gates applied: no_behavioural_pass, no_license.

Audited 2026-10-08 · audit v0.4.1 · source sha 7d968c432be9full audit observations/trust-audit/mcp-server/mnhlt__websearch.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-087d968c432be9SAFEB89first audit
06

Questions

What is the WebSearch MCP server?

[Self-hosted] A Model Context Protocol (MCP) server implementation that provides a web search capability over stdio transport. This server integrates with a WebSearch Crawler API to retrieve search results.

What tools does WebSearch expose?

1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is WebSearch safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does WebSearch need?

No credential environment variables were found in its source, so it appears to need none.

How does WebSearch run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as websearch-mcp at 1.0.2.

How current is this page?

The grade is for one exact copy of the source (7d968c432be9), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement